Weijie Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Weijie Bai has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Jinsheng Xiao
Wuhan University
1 shared publication Qingkun Huang
School of Computers, Guangdong University of Technology, Guangzhou, China
1 shared publication- Yunhua Chen
School of Computer Science and Engineering, Guangdong University of Technology, Guangzhou 510006, China
1 shared publication
Latest Publications
- 22 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 14 (4) , 1544-1552
Efficient Motion Symbol Detection and Multikernel Learning for AER Object Recognition
Address event representation (AER) vision sensors process visual information by monitoring changes in light intensity and generating event streams. In this paper, a threshold mechanism based on the statistical results of the peak membrane potentials, is proposed to improve the accuracy and efficiency of the motion symbol detection (MSD) method based on the leaky integrate-and-fire (LIF) neuron model and a peak spiking monitoring unit (PSMU). And a multi-kernel learning algorithm based on the tempotron rule, namely MK-tempotron, is proposed to improve the antinoise performance of the classifier. In MK-tempotron, different kernels are applied to calculate the post-synaptic membrane potentials (PSPs) according to different input spiking patterns, to counteract the impact of noise on the spiking activities, so that the synaptic weights can be changed in the direction of correct firing. We verified the effectiveness of the threshold mechanism and multi-kernel learning on a variety of data sets. The experimental results show that among the several recent algorithms based on temporal encoding and SNN classifier, which have advantages in power consumption and network latency, our method achieved the best accuracy on MNIST-DVS (100ms) and N-CARS, and it also achieved competitive results on N-MNIST, CIFAR10-DVS, Posture-DVS, Poker-DVS and MNIST-DVS (200ms/500ms/2000ms).
- 22 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 14 (4) , 1544-1552
Efficient Motion Symbol Detection and Multikernel Learning for AER Object Recognition
Address event representation (AER) vision sensors process visual information by monitoring changes in light intensity and generating event streams. In this paper, a threshold mechanism based on the statistical results of the peak membrane potentials, is proposed to improve the accuracy and efficiency of the motion symbol detection (MSD) method based on the leaky integrate-and-fire (LIF) neuron model and a peak spiking monitoring unit (PSMU). And a multi-kernel learning algorithm based on the tempotron rule, namely MK-tempotron, is proposed to improve the antinoise performance of the classifier. In MK-tempotron, different kernels are applied to calculate the post-synaptic membrane potentials (PSPs) according to different input spiking patterns, to counteract the impact of noise on the spiking activities, so that the synaptic weights can be changed in the direction of correct firing. We verified the effectiveness of the threshold mechanism and multi-kernel learning on a variety of data sets. The experimental results show that among the several recent algorithms based on temporal encoding and SNN classifier, which have advantages in power consumption and network latency, our method achieved the best accuracy on MNIST-DVS (100ms) and N-CARS, and it also achieved competitive results on N-MNIST, CIFAR10-DVS, Posture-DVS, Poker-DVS and MNIST-DVS (200ms/500ms/2000ms).